{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:72UO6WMR6BUVKJW25YCGWDKMKA","short_pith_number":"pith:72UO6WMR","canonical_record":{"source":{"id":"2502.04997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T15:19:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"391eb350cb7b8150b8e9636da52d4d0a6affcce22bb411175ff8873253e8c8d0","abstract_canon_sha256":"385899a3f02edd6da017b04232b790c852cf6ce2e539e97907fb435f1fe95990"},"schema_version":"1.0"},"canonical_sha256":"fea8ef5991f0695526daee046b0d4c5000f567a34c01829894c737c179ed565a","source":{"kind":"arxiv","id":"2502.04997","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04997","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04997v1","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04997","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"72UO6WMR6BUV","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"72UO6WMR6BUVKJW2","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"72UO6WMR","created_at":"2026-07-05T10:11:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:72UO6WMR6BUVKJW25YCGWDKMKA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T15:19:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"391eb350cb7b8150b8e9636da52d4d0a6affcce22bb411175ff8873253e8c8d0","abstract_canon_sha256":"385899a3f02edd6da017b04232b790c852cf6ce2e539e97907fb435f1fe95990"},"schema_version":"1.0"},"canonical_sha256":"fea8ef5991f0695526daee046b0d4c5000f567a34c01829894c737c179ed565a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:01.144682Z","signature_b64":"VyZ4CPmNaADKWWxSqL6ayWjvFrva8rU57OgdrtltvjDo566sSo3J+XR2MziNQulJF7rhA1rHKgQTmEov5x6OCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fea8ef5991f0695526daee046b0d4c5000f567a34c01829894c737c179ed565a","last_reissued_at":"2026-07-05T10:11:01.144154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:01.144154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04997","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9y1lMwnn6tsRQAciYDOp3chELwaZ3ckWW3Bz+hgWTY2t4MJaSJ+MDBYHb6JCGK4v/52A40TCXFiiimM0+HKVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:29:28.791587Z"},"content_sha256":"36d6d6a5214b5a415a4c771faf1338c04afe1cefa3ab3ad2e8f97a4bea310d25","schema_version":"1.0","event_id":"sha256:36d6d6a5214b5a415a4c771faf1338c04afe1cefa3ab3ad2e8f97a4bea310d25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:72UO6WMR6BUVKJW25YCGWDKMKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Black-box Language Models with Human Judgments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gen Suzuki, Gerrit J. J. van den Burg, Murat Sensoy, Wei Liu","submitted_at":"2025-02-07T15:19:40Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as automated judges to evaluate recommendation systems, search engines, and other subjective tasks, where relying on human evaluators can be costly, time-consuming, and unscalable. LLMs offer an efficient solution for continuous, automated evaluation. However, since the systems that are built and improved with these judgments are ultimately designed for human use, it is crucial that LLM judgments align closely with human evaluators to ensure such systems remain human-centered. On the other hand, aligning LLM judgments with human evaluators is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04997","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.04997/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJUOvsPcRdFExrQfKdGL7qMWNRjurcTfv0TELTyzdU/KlM8SIeFu6SDPyrMbm22QRBgL8mX8UwALklzY4381Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:29:28.792469Z"},"content_sha256":"5b4c225675d180cd49cac1ba6ec94809c0f81b65c724ef19c183b1dffbe28937","schema_version":"1.0","event_id":"sha256:5b4c225675d180cd49cac1ba6ec94809c0f81b65c724ef19c183b1dffbe28937"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72UO6WMR6BUVKJW25YCGWDKMKA/bundle.json","state_url":"https://pith.science/pith/72UO6WMR6BUVKJW25YCGWDKMKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72UO6WMR6BUVKJW25YCGWDKMKA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T08:29:28Z","links":{"resolver":"https://pith.science/pith/72UO6WMR6BUVKJW25YCGWDKMKA","bundle":"https://pith.science/pith/72UO6WMR6BUVKJW25YCGWDKMKA/bundle.json","state":"https://pith.science/pith/72UO6WMR6BUVKJW25YCGWDKMKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72UO6WMR6BUVKJW25YCGWDKMKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:72UO6WMR6BUVKJW25YCGWDKMKA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"385899a3f02edd6da017b04232b790c852cf6ce2e539e97907fb435f1fe95990","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T15:19:40Z","title_canon_sha256":"391eb350cb7b8150b8e9636da52d4d0a6affcce22bb411175ff8873253e8c8d0"},"schema_version":"1.0","source":{"id":"2502.04997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04997","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04997v1","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04997","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"72UO6WMR6BUV","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"72UO6WMR6BUVKJW2","created_at":"2026-07-05T10:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"72UO6WMR","created_at":"2026-07-05T10:11:01Z"}],"graph_snapshots":[{"event_id":"sha256:5b4c225675d180cd49cac1ba6ec94809c0f81b65c724ef19c183b1dffbe28937","target":"graph","created_at":"2026-07-05T10:11:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.04997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used as automated judges to evaluate recommendation systems, search engines, and other subjective tasks, where relying on human evaluators can be costly, time-consuming, and unscalable. LLMs offer an efficient solution for continuous, automated evaluation. However, since the systems that are built and improved with these judgments are ultimately designed for human use, it is crucial that LLM judgments align closely with human evaluators to ensure such systems remain human-centered. On the other hand, aligning LLM judgments with human evaluators is ","authors_text":"Gen Suzuki, Gerrit J. J. van den Burg, Murat Sensoy, Wei Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T15:19:40Z","title":"Aligning Black-box Language Models with Human Judgments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04997","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36d6d6a5214b5a415a4c771faf1338c04afe1cefa3ab3ad2e8f97a4bea310d25","target":"record","created_at":"2026-07-05T10:11:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"385899a3f02edd6da017b04232b790c852cf6ce2e539e97907fb435f1fe95990","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T15:19:40Z","title_canon_sha256":"391eb350cb7b8150b8e9636da52d4d0a6affcce22bb411175ff8873253e8c8d0"},"schema_version":"1.0","source":{"id":"2502.04997","kind":"arxiv","version":1}},"canonical_sha256":"fea8ef5991f0695526daee046b0d4c5000f567a34c01829894c737c179ed565a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fea8ef5991f0695526daee046b0d4c5000f567a34c01829894c737c179ed565a","first_computed_at":"2026-07-05T10:11:01.144154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:01.144154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VyZ4CPmNaADKWWxSqL6ayWjvFrva8rU57OgdrtltvjDo566sSo3J+XR2MziNQulJF7rhA1rHKgQTmEov5x6OCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:01.144682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36d6d6a5214b5a415a4c771faf1338c04afe1cefa3ab3ad2e8f97a4bea310d25","sha256:5b4c225675d180cd49cac1ba6ec94809c0f81b65c724ef19c183b1dffbe28937"],"state_sha256":"fa828ebd60e963e9dcc68d1a613d045d7cfbf9229e88fdb234ae64028593b273"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ms7HpmmNxnOywfWH2uj2WS5z+7pTL45gsCN1oxrKGlLZ+0he3thlldV8JhUz4mLy/HlKwA+ytNxtfIaKTpyuCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:29:28.805258Z","bundle_sha256":"7a2a6c67d9dcd5de7f316f928c50a0d1b8de9e6c4ff4d444b6a25fb5d8848996"}}